Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds concrete behavioral constraints beyond them: currency unit, the +50% per-change cap, the +100% cumulative 24h cap, the -80% cut floor, and the preview/apply semantics of confirm. This is exactly the guardrail context an agent needs before a clamped mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action, then guardrails, then the control flag. No filler; every clause carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description supplies the guardrails, currency, and confirm behavior, but omits parameter-level detail for the two IDs, leaving a minor gap for a 4-param tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the parameter burden. It clarifies budget (unit = main unit of account currency) and confirm (preview vs apply), but says nothing about advertiser_id or adgroup_id, leaving half the parameters undocumented in text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Updates a TikTok ad group budget'), which cleanly separates it from sibling update_tiktok_adgroup (the entity itself) and update_tiktok_campaign_budget (campaign level). It does not name those siblings explicitly, so differentiation is by resource specificity rather than explicit routing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an actionable invocation pattern via the confirm flag ('confirm=false previews, confirm=true applies'), which tells the agent to preview before applying. It does not, however, state when to use this tool versus alternatives like campaign-level budget updates or other budget tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.